Research map / Image generation / Text-to-image diffusion
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
Zeyu Chen, Fangmin Zhao, Yan Shu, Yichao Liu, Liu Yu, Yu Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add textual style branch to the style encoder (ablation) | StyleTextGen · StyleText-CE (ablation) | FID: 133.62 -> 113.47 | Improved |
| add visual prior branch to the style encoder (ablation) | StyleTextGen · StyleText-CE (ablation) | FID: 124.18 -> 113.47 | Improved |
| add text style consistency loss (ablation) | StyleTextGen · StyleText-CE (ablation) | FID: 126.94 -> 113.47 | Improved |
| add inference-time style injection (ablation) | StyleTextGen · StyleText-CE (ablation) | FID: 118.36 -> 113.47 | Improved |
| add textual style branch (ablation) | StyleTextGen · StyleText-CE (ablation) | Sen.Acc: 0.618 -> 0.659 | Improved |
| add text style consistency loss (ablation) | StyleTextGen · StyleText-CE (ablation) | Sen.Acc: 0.629 -> 0.659 | Improved |
| replace TextFlux with StyleTextGen on AnyWord-Eval English | TextFlux · AnyWord-Eval English | Sen.Acc: 0.6542 -> 0.7102 | Improved |
| replace TextFlux with StyleTextGen on AnyWord-Eval English | TextFlux · AnyWord-Eval English | FID: 59.44 -> 49.51 | Improved |
| replace Calligrapher with StyleTextGen, external-style reference | Calligrapher · StyleText-CE external-style | Sen.Acc / NED: Sen.Acc and NED increase by 0.135 and 0.11 | Improved |
| replace Calligrapher with StyleTextGen, self-style reference | Calligrapher · StyleText-CE self-style | Sen.Acc / NED: Sen.Acc and NED improve by 0.11 and 0.095 | Improved |
Closest papers by meaning
- Towards Visual Text Design Transfer Across Languages (NeurIPS 2024 · similarity 0.90)
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.88)
- StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements (CVPR 2025 · similarity 0.87)
- Layout-Agnostic Scene Text Image Synthesis with Diffusion Models (CVPR 2024 · similarity 0.87)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.86)
- Text to Sketch Generation with Multi-Styles (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
